Dynamics of Sows’ Activity Housed in Farrowing Pens with Possibility of Temporary Crating might Indicate the Time When Sows Should be Confined in a Crate before the Onset of Farrowing

Abstract

Simple Summary: In natural conditions, before the onset of farrowing, sows build a nest mainly to protect piglets from adverse weather conditions and predators. In modern commercial farms nest-building behaviour is limited, because, during the period of nest building, sows are confined in a farrowing crate. This has a negative effect on sow welfare. Recently, the concept of temporary crating has been introduced to achieve a compromise between the needs of the sow and her piglets. According to this concept, sows could be kept out of the crate at the time of prenatal nest-building behaviour and after the critical period of piglets' life. In this study, we developed a method to monitor sows' behaviour on the basis of accelerometer data. The developed monitoring method provides the following two types of alarms: A "first-stage" alarm that indicates the beginning of nest-building behaviour, with a median of 8 h 51 min before the onset of farrowing and a "second-stage" alarm that indicates the end of nest-building behaviour with a median of 2 h 3 min before the onset of farrowing. On the basis of these two types of alarms a farmer can make a decision when to provide adequate nest-building material and when to confine a sow in a crate for protection of the piglets' welfare. Abstract: One way to reduce the negative impact of farrowing crates on sow welfare is to limit confinement of sows from the onset of farrowing until the end of the critical period of piglets' life a few days after farrowing. In order to provide an indication of the time when sows should be confined in crates, ear tag-based acceleration data was modeled to provide the following two types of alarms: A "first-stage" alarm that indicates the beginning of nest-building behaviour, and a "second-stage" alarm that indicates the ending of the nest-building behaviour. In total, 53 sows were included in the experiment. Each sow had an ear tag with an accelerometer sensor mounted on the ear. Acceleration data were modeled with the Kalman filtering and fixed interval smoothing (KALMSMO) algorithm. It was possible to predict farrowing on the basis of increased activity in the validation dataset with a median of 8 h 51 min before the onset of farrowing. Alarms that indicated the need for confinement of the sow in a crate were generated with a median of 2 h 3 min before the onset of farrowing. These results suggest that the developed model should be sufficient to provide early warning of approaching farrowing and secondary alarm indicating the need to confine a sow in a crate.

Where is the sow’s nose: RetinaNet object detector as a basis for monitoring the use of rack with nest-building material

“…Analysis of manually labeled pulling hay and all hay rack use behaviors and comparison of these variables to the automatically estimated activity level of sows in a period from introduction to the farrowing pen until farrowing indicate high variability of expressed hay rack-oriented behaviors. In 11 out of 12 sows, the increase in activity level was very clear with a peak visible several hours before the start of farrowing , which is consistent with the reported dynamics of sows' activity level in this period (Oczak et al, 2019). In contrast, only six out of 12 sows reached their peak of labeled hay rack use and pulling hay behaviors at the same time as their peak of activity level (e.g., Figure 10).…”

“…Additionally, our hypothesis is that automated monitoring of rack use by sows might improve the performance of models for farrowing prediction, which are based only on the general activity level of animals. This might be especially relevant for improving sow welfare in farrowing systems designed for temporary sow confinement in crates (Oczak et al, 2019).…”

“…In this study, we aimed to develop a computer vision algorithm based on an object detection model for monitoring the use of the dispenser with nest-building material in preparturient sows. The second objective was to analyze if the output of this algorithm could potentially improve the performance of farrowing prediction compared to current state-of-the-art techniques for farrowing prediction based solely on activity levels (Manteuffel et al, 2015;Pastell et al, 2016;Traulsen et al, 2018;Oczak et al, 2019).…”

Information Technologies for Welfare Monitoring in Pigs and Their Relation to Welfare Quality®

“…Body dimension (G), weight (G), movement (G, S), farrowing alarms (S) [32,[38][39][40][41][42]45,49,62,64,68,[88][89][90][91]93,96] a A: abattoir, G: growing pigs, P: piglets, S: sows. Stress vocalisation (G, P), object manipulation (G), defence cascade response (G), pig face recognition (S) [33,57,66,74,76,[79][80][81]87] a A: abattoir, G: growing pigs, P: piglets, S: sows.…”

Automated detection of sow posture changes with millimeter-wave radars and deep learning

“…Invasive technologies include sensors attached to the animals, such as accelerometers that record the acceleration and orientation of the sow across time. These sensors are typically embedded in an ear tag (Traulsen et al 2018, Oczak et al 2020), a collar (Cornou et al, 2011), a harness (Canario et al, 2018), or fastened to one leg (Ringenbberg et al 2010). However, as piglets grow, they increasingly explore their environment and are likely to chew the device insistently, which may lead the sow to change posture and activity if the discomfort is significant.…”